brandonbeiler/InternVL3_5-GPT-OSS-20B-A4B-Preview-FP8-Dynamic Image-Text-to-Text • 21B • Updated Aug 30, 2025 • 16 • 2
Running on Zero Featured 837 Florence 2 📉 837 Perform image captioning, detection, OCR and more with Florence‑2
Running on Zero MCP 57 Multimodal VLM Thinking 🥠 57 Lumian-VLR / VisionThink / MiniCPM-V / Typhoon-OCR / olmOCR